JP6502135B2 - Fall detection terminal and program - Google Patents

Description

  The present invention relates to a fall detection terminal having a function of detecting a fall of a user (carried person).

  Conventionally, methods for detecting a fall of a person have been proposed. For example, in the method of Patent Document 1, whether the absolute value (acceleration absolute value) of the acceleration digital signal value obtained from the acceleration sensor attached to the trunk of a person is equal to or greater than a threshold, ie, in normal operation such as walking A fall of a person is detected based on whether a large acceleration that is rarely detected is detected. Further, in the method of Patent Document 2, a fall of a person is detected based on whether or not an acceleration sensor fixed to the human body detects an acceleration close to free fall.

JP, 2009-163538, A JP 2004-252618 A

  However, the fall mode is various and in many cases difficult to detect by the conventional fall detection method. For example, when a person loses consciousness and falls down, although free fall characteristics are easily observed due to weakness, the impact tends to be small because the head and body first collide with the ground. On the other hand, when falling down in a conscious state, such as when it falls down, the arm is moved to protect the body, so the free fall characteristic tends to be difficult to observe. Therefore, as in the prior art, there has been a problem that it is difficult to determine the fall with high accuracy by merely observing only the absolute value (peak value) of the acceleration or merely the fall characteristic.

  This invention is made in view of said subject, and it aims at providing the fall detection terminal which can perform a highly accurate fall determination.

  The fall detection terminal according to the present invention is carried by a user, and in the fall detection terminal for detecting a fall of the user, a movement sensor for detecting movement of the fall detection terminal and outputting movement data, and the movement data Impact detection means for detecting an impact generated at the fall detection terminal and calculating an impact evaluation value indicating a possibility of falling based on the impact; and drop characteristics that appear when the fall detection terminal falls freely from the movement data The user uses the drop detection means for detecting and calculating a drop evaluation value indicating the possibility of falling based on the drop characteristic, and the user based on the overall evaluation value obtained by comprehensively evaluating the impact evaluation value and the drop evaluation value. And a fall determination unit that determines whether or not the vehicle has fallen.

  With this configuration, the fall possibility (impact evaluation value) based on the impact is determined from the magnitude of the impact applied when falling, and the fall characteristic based on the fall characteristic from the fall characteristic of the free fall generated in the process leading to the fall. Determine the possibility (fall evaluation value). And it is judged whether the user has fallen based on the comprehensive evaluation value which comprehensively evaluated the fall possibility (fall evaluation value) based on the fall possibility (impact evaluation value) based on impact and the fall characteristic ( Perform fall judgment). Thereby, it is possible to perform the fall determination with high accuracy as compared with the case where it is determined only from the peak value of the acceleration or only the drop characteristic.

  Further, in the fall detection terminal of the present invention, the fall determination means calculates the amount of activity of the user from the movement data, and corresponds to the amount of activity of the user in a predetermined period based on the time of occurrence of the impact. The total evaluation value may be determined by weighting the impact evaluation value and the drop evaluation value.

  With this configuration, the amount of activity of the user is calculated from the movement data, and when calculating the comprehensive evaluation value, the impact evaluation value and the drop are calculated according to the amount of activity for a predetermined period based on the time of impact (falling). Weights are added to the evaluation value. Therefore, it is possible to perform the fall determination with high accuracy based on the comprehensive evaluation value in consideration of the activity amount (activity state) of the user at the time of the fall.

  Further, in the fall detection terminal according to the present invention, the fall judging means performs the drop evaluation based on the impact evaluation value when the activity amount of the user in the predetermined period before the occurrence of the impact is smaller than the reference activity amount. The weight of the value may be increased to obtain the total evaluation value.

  With this configuration, when the amount of activity before the occurrence of an impact is small, that is, when the user before the occurrence of an impact is at rest, the weight of the drop evaluation value is made higher than the impact evaluation value. When a user who has been at rest falls due to loss of consciousness etc., the fall evaluation value is more likely to reflect the possibility of falling than the impact evaluation value. Therefore, it is possible to determine with high accuracy the falling of the user who has been resting (for example, falling due to loss of consciousness).

  Further, in the fall detection terminal according to the present invention, the fall detection means detects the fall characteristic from the movement data in a first predetermined period before the occurrence of the impact, and the fall determination means detects the occurrence of the impact before the occurrence of the impact. The activity amount of the user may be calculated from the movement data of a second predetermined period which is longer than the first predetermined period.

  With this configuration, the drop characteristic can be appropriately detected from the movement data of the first predetermined period before the occurrence of the impact, and the user's activity amount can be detected in the second predetermined period before the occurrence of the impact (the first predetermined period Can be appropriately calculated from motion data of a period longer than a predetermined period of

  In the fall detection terminal of the present invention, the second predetermined period may be set so as not to include the first predetermined period.

  With this configuration, it is possible to appropriately calculate the amount of activity of the user from motion data in a second predetermined period (a period not including the first predetermined period) before the occurrence of an impact.

  The fall detection terminal according to the present invention is carried by a user, and the fall detection terminal detects a fall of the user, and detects movement of the user and outputs movement data indicating the movement of the user. Shock detection means for detecting an impact generated at the fall detection terminal from the movement data, fall detection means for detecting a fall characteristic appearing when the fall detection terminal falls freely from the movement data, and And a fall determination unit that determines whether the user has fallen based on the detection result and the detection result of the fall characteristic, the fall determination unit determining the amount of activity of the user from the movement data. When the user's activity amount in a predetermined period with reference to the time of occurrence of the impact is in a resting state smaller than the reference activity amount, detection of the drop characteristic from the detection result of the impact By increasing the weighting of the results to determine whether the user has fallen.

  With this configuration, it is determined whether or not the user has fallen (fall determination) based on the detection result of the impact applied when falling and the detection result of free fall falling characteristics generated in the process of falling down (falling down) I do. In this case, the amount of activity of the user is calculated from the movement data, and weights are added to the detection result of the impact and the detection result of the falling characteristic according to the activity amount of the predetermined period based on the occurrence of impact (at the time of falling). Be When the amount of activity before the occurrence of an impact is small, that is, when the user is at rest, the weight of the detection result of the drop characteristic is made higher than the detection result of the impact. When a user who has been at rest falls due to loss of consciousness etc., the fall evaluation value is more likely to reflect the possibility of falling than the impact evaluation value. Therefore, it is possible to determine with high accuracy the falling of the user who has been resting (for example, falling due to loss of consciousness).

  The program according to the present invention is a program executed by a fall detection terminal for detecting a fall of a user, and the fall detection terminal is a motion sensor for detecting the movement of the fall detection terminal and outputting movement data. The program includes a process of causing a computer to detect an impact generated on the fall detection terminal from the movement data, and calculating an impact evaluation value indicating a possibility of falling based on the impact, and the movement data A process of detecting a fall characteristic that appears when the fall detection terminal falls freely, and calculating a fall evaluation value indicating a possibility of falling based on the fall characteristic, and comprehensively evaluating the impact evaluation value and the fall evaluation value And a process of determining whether the user has fallen based on the integrated evaluation value.

  As with the above terminal, this program also determines the fall possibility (impact evaluation value) based on the impact from the magnitude of the impact applied when falling, and the free fall drop characteristics generated in the process of falling. From this, the fall possibility (drop evaluation value) based on the drop characteristics is determined. And it is judged whether the user has fallen based on the comprehensive evaluation value which comprehensively evaluated the fall possibility (fall evaluation value) based on the fall possibility (impact evaluation value) based on impact and the fall characteristic ( Perform fall judgment). Thereby, it is possible to perform the fall determination with high accuracy as compared with the case where it is determined only from the peak value of the acceleration or only the drop characteristic.

  According to the present invention, it is possible to perform a highly accurate fall determination by comprehensively evaluating the magnitude of the impact and the free fall characteristics and determining the fall.

It is a block diagram of the fall detection terminal in embodiment of this invention. (A) It is a figure which shows an example of the acceleration data of fall. (B) It is a figure which shows an example of the acceleration data of a non fall (when a hand is hit against a wall). (A) It is a figure which shows an example of the fall fall acceleration data. (B) It is a figure which shows an example of the acceleration data of the fall during walking. (C) It is a figure which shows an example of the acceleration data of falling during driving | running | working. It is a flowchart for operation | movement explanation of the fall detection terminal in embodiment of this invention.

  Hereinafter, a fall detection terminal according to an embodiment of the present invention will be described using the drawings. The present embodiment exemplifies the case of a fall detection terminal used in a monitoring system or the like for detecting a fall of an elderly person. The function (fall detection function) of the fall detection terminal can be realized by a program stored in a memory or the like of the terminal.

  The fall detection terminal is a terminal device carried by a user (such as an elderly person). For example, the fall detection terminal is configured of a wristband type (watch type) wearable terminal, and a user (such as an elderly person) is attached to a wrist or an arm. The fall detection terminal may be a pendant type that hangs from the neck, may be a head-mounted type that is worn on the head or ear, or may be a waist-mounted type such as a belt type.

  First, the configuration of the overturn detection terminal of the present embodiment will be described with reference to the drawings. FIG. 1 is a block diagram showing the configuration of the fall detection terminal according to the present embodiment. As shown in FIG. 1, the fall detection terminal 1 includes an acceleration sensor 2, a mounting sensor 3, an altitude sensor 4, and a rescue button 5. The fall detection terminal 1 further includes an operation display unit 6, a vibration unit 7, a power supply unit 8, a wireless communication unit 9, and a monitoring control unit 10.

  The acceleration sensor 2 is a sensor having a function of detecting a motion of the user and outputting motion data (acceleration data) indicating the motion of the user, and is formed of, for example, a 3-axis acceleration sensor. The acceleration sensor 2 outputs acceleration data detected at a predetermined sampling cycle. The wearing sensor 3 is a sensor having a function of detecting a wearing state (whether or not worn) to a human body (arm), and for example, the contact or proximity of the human body wearing part such as a capacitance type sensor Composed of sensors that can be detected in The altitude sensor 4 is a sensor having a function of detecting a change in height of the terminal using a change in air pressure or the like, and is constituted by, for example, a pressure sensor. The emergency button 5 is an operation unit (emergency operation unit) for the user to make an emergency call in an emergency.

  The operation display unit 6 includes, for example, a touch panel display, and has a function (information display function) for displaying various types of information such as abnormality notification and a function (input operation function) for performing various input operations such as cancel operation. There is. The vibration unit 7 is configured of a vibration device or the like, and has a function of notifying the user of an abnormality, an operation reception, or the like by stimulation by vibration. The power supply unit 8 is configured by a battery such as a battery. The wireless communication unit 9 has a function of performing wireless communication with the security terminal 12 installed at the remote monitoring center 11 via, for example, a mobile communication network. In addition, the wireless communication unit 9 has a function of performing wireless communication with a security terminal (not shown) installed in the home by Bluetooth (registered trademark), specified low power wireless communication, or the like.

  The monitoring control unit 10 has a function of performing emergency monitoring based on inputs from the sensors (acceleration sensor 2, attachment sensor 3, altitude sensor 4) and the operation unit (emergency button 5 and operation display unit 6). It includes a part 13, a life monitoring part 14 having a function of monitoring the life, and a fall monitoring part 15 having a function of monitoring a fall. Further, the monitoring control unit 10 has a function of controlling each part of the overturn detection terminal 1.

  The emergency monitoring unit 13 has a function of performing an emergency report to the monitoring center 11 when the user operates the emergency button 5 for emergency response. For example, when the emergency button 5 is continuously pressed for 2 seconds, it is determined that the emergency is abnormal, and the emergency abnormality is reported to the monitoring center 11, and the fact that the abnormality is determined is notified to the surroundings by vibration, screen, sound, light or the like. Because the emergency abnormality is an abnormal operation, the cancellation operation is not accepted. In addition, even if the life abnormality and the fall abnormality (to be described later) occur, if the emergency abnormality occurs, the emergency abnormality is prioritized.

  Based on the output of the acceleration sensor 2, the life monitoring unit 14 monitors whether the user (carried person or wearer) is moving to such an extent that it occurs in daily life, and that the immobile condition continues due to sudden illness or the like. It has a function to notify. The life monitoring unit 14 performs life monitoring in the wearing state (wearing state). For example, the movement (body movement) of the user is detected from the output of the acceleration sensor 2, and it is determined that life abnormality occurs if body movement at the daily life level does not continuously occur for a fixed period (for example, one hour). If it is determined that the life is abnormal, the user is notified of the fact by vibration, screen, sound, light and the like. The life monitoring unit 14 cancels the life abnormality if a body movement is detected within a predetermined cancellation time (for example, 10 seconds) or a cancellation operation is input after it is determined and notified that the life is abnormal Do not report any abnormality) The detection process of body movement is the same as the process in the fall monitoring (described later).

  The fall monitoring unit 15 has a function of automatically detecting the fall of the user (carried person, wearer) based on the output of the acceleration sensor 2 and reporting the occurrence of the fall accident. The fall monitoring unit 15 performs the fall monitoring in the mounted state (in the mounted state). In this case, "impact" and "free fall characteristics" are detected from the output of the acceleration sensor 2, and the detection result is evaluated to detect a fall. Then, after detecting a fall, if a body movement such as standing up and walking can not be detected for a predetermined time (for example, 15 seconds), it is determined that the fall is abnormal. The predetermined time does not include several seconds (for example, 5 seconds) immediately after the fall detection. Then, when it is determined that the fall is abnormal, the user is notified of the fact by vibration, screen, sound, light and the like. The fall monitoring unit 15 cancels the fall abnormality (does not report any abnormality) if a cancellation operation is input during a predetermined cancellation time (for example, 20 seconds) after determining and notifying that the fall abnormality.

  Here, the basic logic of the fall detection will be described with reference to FIG. The fall monitoring unit 15 detects a fall by evaluating the impact applied to the terminal at the time of the fall and the falling characteristics generated in the process leading to the fall. In the present invention, in particular, the fall likeness based on impact and the fall likeness based on the fall characteristics are comprehensively evaluated to make a final fall judgment. As a configuration for that purpose, the fall monitoring unit 15 includes an impact detection unit 16, a drop detection unit 17, and a fall determination unit 18.

  The impact detection unit 16 has a function of detecting an impact generated on the overturn detection terminal 1 from the acceleration data and calculating an impact evaluation value indicating a possibility of overturning based on the impact. Since the fall is accompanied by a collision of the body to the ground or the like, the acceleration applied to the fall detection terminal 1 changes greatly. Therefore, the impact detection unit 16 is configured to detect an impact applied to the terminal at the time of falling, based on the peak value of the acceleration.

2 and 3 are diagrams showing examples of acceleration data. In this case, as pre-processing, acceleration data output for each of the three axes (X axis, Y axis, Z axis) is scalarized and subjected to moving average processing (low pass filter). The impact detection unit 16 detects a peak (time T1) of acceleration equal to or higher than a predetermined threshold (for example, 30 m / sec ² ), and obtains the peak value P thereof. Then, the impact detection unit 16 obtains the impact evaluation value Es based on the peak value P by using, for example, the following Expression 1. Here, c is an adjustment factor for the overall evaluation.
Es = P x c (Equation 1)

The fall detection unit 17 has a function of detecting a fall characteristic that appears when the overturn detection terminal 1 freely falls from the acceleration data, and calculating a fall evaluation value indicating a possibility of overturning based on the fall characteristic. Falling is a phenomenon that causes a fall toward the ground, so the acceleration during falling is smaller than the gravitational acceleration (9.8 m / sec ² ). Therefore, the fall detection unit 17 goes back in time from the peak of acceleration (time T1), obtains the intersection point (time T2) with the gravitational acceleration, and calculates the average acceleration value A from that point onward to a predetermined period ago (time T3) Do. A period from time T3 to time T2 (for example, 500 msec) can be called a drop determination period. And the fall detection part 17 calculates | requires the fall evaluation value Ef based on the acceleration average value A by using the following formula 2, for example. Here, a is a drop standard constant, and b is an adjustment factor for comprehensive evaluation.
Ef = (a−A) × b (Equation 2)

The constant a is an acceleration serving as a reference point for distinguishing the presence or absence of the falling characteristic, and, for example, 8 m / sec ² or gravitational acceleration 9.8 m / sec ² is used. When the acceleration average value A is smaller than the constant a, the drop evaluation value Ef takes a positive value.

The fall determination unit 18 has a function of determining whether or not the user has fallen, based on the comprehensive evaluation value obtained by comprehensively evaluating the impact evaluation value and the drop evaluation value. There are various fall modes, and the impact may be large and the falling characteristics may be remarkable, but the impact may be small and the falling characteristics may be remarkable. Conversely, the falling characteristics may not be remarkable but the impact may be large. Therefore, the fall judging unit 18 adds the impact evaluation value and the drop evaluation value by using the following equation 3 to obtain the comprehensive evaluation value Et, and is used when the comprehensive evaluation value is equal to or more than the reference value Th of the fall judgment. To detect the fall of the person.
Et = Es + Ef (Equation 3)

  The fall determination unit 18 performs automatic cancellation determination based on body movement detection. Even if a fall is detected, it is considered that the user is not in a dangerous state if body movement is detected thereafter, so that the fall judging unit 18 automatically cancels the fall detection. In this body movement detection (automatic cancellation determination), body movement at a predetermined delay time (for example, 5 seconds) from the peak time point (T1) at the time of fall determination is ignored, and the body movement determination time thereafter (for example, 15 seconds) Determine the presence or absence of body movement during). The determination of the presence or absence of body movement is performed by observing the peak value or the amount of change of acceleration. For example, when a peak value equal to or more than a predetermined threshold value is detected a predetermined number of times, or when the sum of the peak values exceeds a predetermined value, body movement is detected. Alternatively, when the sum of changes in acceleration over a predetermined period (for example, several seconds) or body movement determination time exceeds a certain value, or when the change in acceleration per unit time exceeds a certain value, body movement To detect If the body movement is not detected after the automatic cancellation determination, that is, when the body movement determination time has elapsed, the fall determination unit 18 determines a fall abnormality.

  Further, the fall determination unit 18 performs the fall determination in consideration of the user's activity status (activity amount). The impact and drop characteristics obtained differ depending on the fall mode, such as whether or not you are conscious or if you are moving violently. Therefore, the fall determination unit 18 calculates the amount of activity of the user from the acceleration data, and weights the impact evaluation value and the drop evaluation value according to the amount of activity of the user in a predetermined period based on the occurrence of an impact. In addition, a comprehensive evaluation value is obtained.

  That is, the fall determination unit 18 does not simply calculate the comprehensive evaluation value as “Et = Es + Ef”, but weights each evaluation value (Es, Ef) according to the activity status (activity amount) of the user at the time of the fall. Then, they are added to obtain an overall evaluation value Et. In this case, the activity status (activity amount) of the user analyzes the movement in a fixed period (activity determination period) before the fall (impact) is detected, and acceleration data in the activity determination period (for example 3 seconds) ( It is determined based on the peak and the change amount). In addition, since the movement during falling is included in the above-mentioned fall determination period (for example, the period from time T3 to time T2), this activity determination period (for example, the period from time T4 to time T3) A period before the drop determination period is set without including a period after the drop determination period (for example, a period from time T3 to time T1) (see FIG. 3).

Specifically, the fall determination unit 18 determines an exercise amount W, which is a total change amount of acceleration in the activity determination period, and determines the activity state (severity of movement) by comparing the exercise amount W with the activity reference value. . The amount of movement W is obtained by integrating the differences of acceleration data (scalarized acceleration data a1, a2, ..., an-1, an) in the activity determination period by using, for example, the following equation 4. Can. The momentum W may be calculated for each of the three axes (X axis, Y axis, Z axis), or may be calculated as the sum or average of the three axes.
W = | a1-a2 | + | a2-a3 | +... + | An-1-an | (equation 4)

  The amount of movement W can also be determined based on the magnitude of the peak value and the number of times of detection. For example, the amount of movement W may be the number of times a peak value above a certain level is detected, may be the sum of the above peak values, or may be the number weighted by the maximum or average of the above peak values.

In the present embodiment, the fall determination unit 18 sets the weight of the drop evaluation value higher than the impact evaluation value when the user's activity amount in the predetermined period before the occurrence of the impact is smaller than the reference activity amount. Determine the evaluation value. That is, when the amount of movement W is very small and the state immediately before falling is a resting state (such as upright immobility), the overall evaluation value Et is obtained by weighting so that the drop evaluation Ef is more important than the impact evaluation value Es. For example, when the amount of movement W is smaller than the reference amount of activity Th1 (the total amount of change is extremely small), weighting processing as shown in the following Expression 5 is performed. The weighting coefficient may be changed according to the amount of exercise W so that the smaller the amount of movement W (the farther from Th1), the smaller Es (the larger Ef) is corrected.
Et = Es × 1/2 + Ef × 3/2 (Equation 5)

  Next, the operation of the overturn detection terminal 1 of the present embodiment will be described with reference to the flow chart of FIG. In the fall detection terminal 1 of the present embodiment, first, a peak is detected from the acceleration data to calculate the impact evaluation value Es (S1), and a free fall characteristic is detected from the acceleration data to calculate the fall evaluation value Ef. (S2). Then, after determining the amount of activity of the user, the impact evaluation value Es and the drop evaluation value Ef are weighted to calculate the comprehensive evaluation value Et (S3), and the user falls based on the comprehensive evaluation value Et It is determined whether or not it is (S4).

  If it is determined that a fall is made, the fall flag is turned ON (S5). Thereafter, body movement detection (automatic cancellation determination) is performed. When the body movement is detected (S6), the overturn flag is turned off (S7). On the other hand, if no body movement is detected (S6), after a predetermined cancellation time has elapsed (S8), a fall abnormality is determined (S9).

  According to the fall detection terminal 1 of the present embodiment, the possibility of falling due to an impact (impact evaluation value Es) is determined from the magnitude of the impact applied when falling, and it occurs in the process leading to the fall. From the fall characteristics of the free fall, the fall possibility (drop evaluation value Ef) based on the fall characteristic is determined. Then, whether or not the user falls over on the basis of the comprehensive evaluation value Et which comprehensively evaluates the possibility of falling (impact evaluation value Es) based on impact and the possibility of falling (fall evaluation value Ef) based on the fall characteristics Make a judgment of (fall judgment). Thereby, it is possible to perform the fall determination with high accuracy as compared with the case where it is determined only from the peak value of the acceleration or only the drop characteristic.

  In short, in the present embodiment, it is determined whether or not the user has fallen based on the detection result of the impact applied when falling and the detection result of the free fall falling characteristic generated in the process leading to the fall. Perform (fall over determination). In this case, the activity amount W of the user is calculated from the acceleration data, and the detection result of the impact and the detection result of the falling characteristic are weighted according to the activity amount W for a predetermined period based on the occurrence of impact (at fall). Is added. When the amount of activity W before the occurrence of an impact is small, that is, when the user is at rest, the weight of the detection result of the falling characteristic is made higher than the detection result of the impact. When a user who has been at rest falls due to loss of consciousness, the fall evaluation value is more likely to reflect the possibility of falling than the impact evaluation value, so fall of the user who has been resting (for example, falling due to loss of consciousness) is highly accurate It is possible to determine

  Further, in the present embodiment, when calculating the comprehensive evaluation value Et, the impact evaluation value Es and the drop evaluation value Ef are weighted according to the amount of activity in a predetermined period based on the occurrence of an impact (when falling). Be added. Therefore, it is possible to perform the fall determination with high accuracy based on the comprehensive evaluation value Et in consideration of the activity amount W (the activity state) of the user at the time of the fall.

  Specifically, when the activity amount W before the occurrence of the impact is small, that is, when the user before the occurrence of the impact is in the resting state, the weighting of the drop evaluation value Ef is made higher than the impact evaluation value Es. As described above, when a user who has been at rest falls due to loss of consciousness, the fall evaluation value is more likely to reflect the possibility of falling than the impact evaluation value, so fall of the user who has been at rest (for example, loss of consciousness It is possible to determine (fall) with high accuracy.

  Further, in the present embodiment, the drop characteristics can be appropriately detected from the acceleration data in the drop determination period (the first predetermined period before the occurrence of an impact). In addition, the amount of activity of the user can be appropriately calculated from the acceleration data in the activity determination period (the second predetermined period before the occurrence of an impact).

  Further, in the present embodiment, the impact detection unit 16 is configured to obtain the impact evaluation value Es based on the peak value P of acceleration, but instead of the peak value P, the total amount of change in acceleration is used. It is good also as composition which detects shock. In this case, the difference with the immediately preceding acceleration data is determined for a predetermined period (for example, 50 msec before and after) based on the detection time of the peak value, the absolute value of this difference is integrated over the predetermined period, and the acceleration change amount h is calculated. . Then, the acceleration change amount h is multiplied by the adjustment coefficient to obtain an impact evaluation value Es. Furthermore, using the acceleration change amount h and the acceleration peak value P in combination, the impact evaluation value Es can also be obtained based on the sum value or the ratio of the two.

  Further, in the present embodiment, the drop detection unit 18 is configured to obtain the drop evaluation value Ef based on the acceleration average value A in the drop determination period, but instead of the acceleration average value A, the drop detection unit 18 in the drop determination period The fall may be detected based on the continuous time or the integration time in which the minimum acceleration or the acceleration below the reference acceleration (constant a) is detected.

  Although the embodiments of the present invention have been described above by way of example, the scope of the present invention is not limited to these, and may be changed or modified according to the purpose within the scope described in the claims. is there.

  As described above, the fall detection terminal according to the present invention has an effect that it is possible to perform the fall determination with high accuracy, and is useful for a monitoring system or the like that detects the fall of the elderly person.

1 fall detection terminal 2 acceleration sensor (motion sensor)
Reference Signs List 3 attached sensor 4 advanced sensor 5 emergency button 6 operation display unit 7 vibration unit 8 power supply unit 9 wireless communication unit 10 monitoring control unit 11 monitoring center 12 security terminal 13 emergency monitoring unit 14 life monitoring unit 15 fall monitoring unit 16 impact detection unit ( Impact detection means)
17 Drop detection unit (drop detection means)
18 Fall judgment unit (fall judgment means)

Claims (6)

In the fall detection terminal which is carried by the user and detects the fall of the user,
A motion sensor that detects motion of the fall detection terminal and outputs motion data;
Impact detection means for detecting an impact generated at the fall detection terminal from the movement data, and calculating an impact evaluation value indicating a possibility of falling based on the impact.
Fall detection means for detecting a fall characteristic that appears when the overturn detection terminal freely falls from the movement data, and calculating a fall evaluation value indicating a possibility of overturning based on the fall characteristic;
Fall determination means for determining whether or not the user has fallen based on the impact evaluation value and a comprehensive evaluation value obtained from the drop evaluation value;
Equipped with
The fall determination means calculates the amount of activity of the user from the movement data, and the impact evaluation value and the drop evaluation according to the amount of activity of the user in a predetermined period based on the time of occurrence of the impact. A fall detection terminal characterized by adding a weight to a value to obtain the comprehensive evaluation value . The fall judging means sets the weight of the drop evaluation value higher than the impact evaluation value to make the comprehensive evaluation, when the activity amount of the user in the predetermined period before the occurrence of the impact is in the resting state smaller than the reference activity amount. obtaining a value, fall detection terminal according to claim 1. The drop detection means detects the drop characteristic from the movement data in a first predetermined period before the occurrence of the impact;
The fall determining means calculates an activity amount of the user from the motion data of the long second predetermined time period than the first predetermined time period but before the occurrence of the impact, to claim 1 or claim 2 Fall detection terminal described. The fall detection terminal according to claim 3 , wherein the second predetermined period is set not to include the first predetermined period. In the fall detection terminal which is carried by the user and detects the fall of the user,
A motion sensor that detects the motion of the user and outputs motion data indicating the motion of the user;
Impact detection means for detecting an impact generated at the fall detection terminal from the movement data;
Drop detection means for detecting a drop characteristic that appears when the fall detection terminal freely falls from the movement data;
Fall determination means for determining whether or not the user has fallen based on the detection result of the impact and the detection result of the drop characteristic;
Equipped with
The fall determination means calculates the amount of activity of the user from the movement data, and the amount of activity of the user in a predetermined period based on the occurrence of the impact is in a resting state smaller than the amount of reference activity. A fall detection terminal characterized by making weighting of a detection result of the drop characteristic higher based on a detection result of an impact and determining whether the user has fallen. A program executed by a fall detection terminal for detecting a fall of a user,
The fall detection terminal is provided with a movement sensor that detects movement of the fall detection terminal and outputs movement data.
The program is a process of causing a computer to detect an impact generated on the fall detection terminal from the movement data, and calculating an impact evaluation value indicating a possibility of falling based on the impact.
A process of detecting a fall characteristic that appears when the fall detection terminal freely falls from the movement data, and calculating a fall evaluation value indicating a possibility of being overturned based on the fall characteristic;
A process of determining whether the user has fallen, based on the impact evaluation value and a comprehensive evaluation value obtained from the drop evaluation value;
Was executed,
In the determination process, the amount of activity of the user is calculated from the movement data, and the impact evaluation value and the drop evaluation are determined according to the amount of activity of the user in a predetermined period based on the occurrence of the impact. A program characterized by adding a weight to a value to obtain the integrated evaluation value .

Images